{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/model-based-reinforcement-learning","name":"Model-based Reinforcement Learning","slug":"model-based-reinforcement-learning","description_markdown":null,"categories":[{"name":"Methodology","url":"/area/methodology"},{"name":"Playing Games","url":"/area/playing-games"},{"name":"Reasoning","url":"/area/reasoning"},{"name":"Robots","url":"/area/robots"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":708,"papers_with_code":234,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":1,"subtasks":0,"parent_tasks":1},"benchmarks":[],"datasets":[{"url":"/dataset/popgym","name":"POPGym","full_name":"Partially Observable Process Gym","num_papers_in_archive":3}],"subtasks":[],"parent_tasks":[{"url":"/task/general-reinforcement-learning","name":"General Reinforcement Learning"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":8,"rows_per_page":100,"shown":100,"of":708,"of_with_code":234,"tagged_in_all":708,"counts":{"archive_papers_tagged":708,"with_a_code_link":234,"where_syntology_ran_a_sample":72,"not_listed_spam_title":0,"listed":708,"listed_where_code_ran":72,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":66,"every_run_a_failure_of_syntologys_instrument":6,"listed_with_a_run_with_no_instrument_failure":66,"listed_every_run_a_failure_of_syntologys_instrument":6,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/when-to-trust-your-model-model-based-policy","slug":"when-to-trust-your-model-model-based-policy","title":"When to Trust Your Model: Model-Based Policy Optimization","date":"2019-06-19","arxiv_id":"1906.08253","repositories_listed":11,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/when-to-trust-your-model-model-based-policy#ran","syntology_url":"https://syntology.ai/paper/1906.08253","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.08253"}},"official":{"repos":["JannerM/mbpo"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/deep-reinforcement-learning-in-a-handful-of","slug":"deep-reinforcement-learning-in-a-handful-of","title":"Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models","date":"2018-05-30","arxiv_id":"1805.12114","repositories_listed":9,"syntology":{"n":19,"n_ran":12,"n_constructed":5,"n_ran_checked":7,"n_instrument":5,"n_unverified":7,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":17,"phrase":"12 ran (of which 5 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 5 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/deep-reinforcement-learning-in-a-handful-of#ran","syntology_url":"https://syntology.ai/paper/1805.12114","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.12114"}},"official":{"repos":["kchua/handful-of-trials"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/neural-network-dynamics-for-model-based-deep","slug":"neural-network-dynamics-for-model-based-deep","title":"Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning","date":"2017-08-08","arxiv_id":"1708.02596","repositories_listed":9,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/neural-network-dynamics-for-model-based-deep#ran","syntology_url":"https://syntology.ai/paper/1708.02596","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1708.02596"}},"official":null}},{"url":"/paper/td-mpc2-scalable-robust-world-models-for","slug":"td-mpc2-scalable-robust-world-models-for","title":"TD-MPC2: Scalable, Robust World Models for Continuous Control","date":"2023-10-25","arxiv_id":"2310.16828","repositories_listed":3,"syntology":{"n":16,"n_ran":12,"n_constructed":4,"n_ran_checked":6,"n_instrument":6,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"12 ran (of which 4 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/td-mpc2-scalable-robust-world-models-for#ran","syntology_url":"https://syntology.ai/paper/2310.16828","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.16828"}},"official":null}},{"url":"/paper/trafficbots-towards-world-models-for","slug":"trafficbots-towards-world-models-for","title":"TrafficBots: Towards World Models for Autonomous Driving Simulation and Motion Prediction","date":"2023-03-07","arxiv_id":"2303.04116","repositories_listed":3,"syntology":null},{"url":"/paper/planning-with-diffusion-for-flexible-behavior","slug":"planning-with-diffusion-for-flexible-behavior","title":"Planning with Diffusion for Flexible Behavior Synthesis","date":"2022-05-20","arxiv_id":"2205.09991","repositories_listed":3,"syntology":null},{"url":"/paper/temporal-predictive-coding-for-model-based","slug":"temporal-predictive-coding-for-model-based","title":"Temporal Predictive Coding For Model-Based Planning In Latent Space","date":"2021-06-14","arxiv_id":"2106.07156","repositories_listed":3,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/temporal-predictive-coding-for-model-based#ran","syntology_url":"https://syntology.ai/paper/2106.07156","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.07156"}},"official":{"repos":["VinAIResearch/TPC-tensorflow","tung-nd/TPC-tensorflow"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/integrated-decision-and-control-towards","slug":"integrated-decision-and-control-towards","title":"Integrated Decision and Control: Towards Interpretable and Computationally Efficient Driving Intelligence","date":"2021-03-18","arxiv_id":"2103.10290","repositories_listed":3,"syntology":null},{"url":"/paper/a-model-based-reinforcement-learning-with","slug":"a-model-based-reinforcement-learning-with","title":"Model-Based Reinforcement Learning with Adversarial Training for Online Recommendation","date":"2019-11-10","arxiv_id":"1911.03845","repositories_listed":3,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/a-model-based-reinforcement-learning-with#ran","syntology_url":"https://syntology.ai/paper/1911.03845","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.03845"}},"official":{"repos":["JianGuanTHU/IRecGAN"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/dynamics-aware-unsupervised-discovery-of","slug":"dynamics-aware-unsupervised-discovery-of","title":"Dynamics-Aware Unsupervised Discovery of Skills","date":"2019-07-02","arxiv_id":"1907.01657","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/dynamics-aware-unsupervised-discovery-of#ran","syntology_url":"https://syntology.ai/paper/1907.01657","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.01657"}},"official":{"repos":["google-research/dads"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/machine-learning-and-system-identification","slug":"machine-learning-and-system-identification","title":"Machine Learning and System Identification for Estimation in Physical Systems","date":"2019-06-05","arxiv_id":"1906.02003","repositories_listed":3,"syntology":null},{"url":"/paper/pipps-flexible-model-based-policy-search","slug":"pipps-flexible-model-based-policy-search","title":"PIPPS: Flexible Model-Based Policy Search Robust to the Curse of Chaos","date":"2019-02-04","arxiv_id":"1902.01240","repositories_listed":3,"syntology":null},{"url":"/paper/synthesizing-neural-network-controllers-with","slug":"synthesizing-neural-network-controllers-with","title":"Synthesizing Neural Network Controllers with Probabilistic Model based Reinforcement Learning","date":"2018-03-06","arxiv_id":"1803.02291","repositories_listed":3,"syntology":null},{"url":"/paper/model-based-reinforcement-learning-for-7","slug":"model-based-reinforcement-learning-for-7","title":"Model-based Reinforcement Learning for Parameterized Action Spaces","date":"2024-04-03","arxiv_id":"2404.03037","repositories_listed":2,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":4,"n_instrument":5,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":9,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/model-based-reinforcement-learning-for-7#ran","syntology_url":"https://syntology.ai/paper/2404.03037","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.03037"}},"official":{"repos":["valarzz/dlpa","valarzz/model-based-reinforcement-learning-for-parameterized-action-spaces"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/the-edge-of-reach-problem-in-offline-model","slug":"the-edge-of-reach-problem-in-offline-model","title":"The Edge-of-Reach Problem in Offline Model-Based Reinforcement Learning","date":"2024-02-19","arxiv_id":"2402.12527","repositories_listed":2,"syntology":null},{"url":"/paper/language-agent-tree-search-unifies-reasoning","slug":"language-agent-tree-search-unifies-reasoning","title":"Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models","date":"2023-10-06","arxiv_id":"2310.04406","repositories_listed":2,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":5,"n_instrument":4,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/language-agent-tree-search-unifies-reasoning#ran","syntology_url":"https://syntology.ai/paper/2310.04406","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.04406"}},"official":{"repos":["lapisrocks/languageagenttreesearch","andyz245/LanguageAgentTreeSearch"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/predictive-experience-replay-for-continual","slug":"predictive-experience-replay-for-continual","title":"Predictive Experience Replay for Continual Visual Control and Forecasting","date":"2023-03-12","arxiv_id":"2303.06572","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/predictive-experience-replay-for-continual#ran","syntology_url":"https://syntology.ai/paper/2303.06572","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.06572"}},"official":{"repos":["wendongzh/continual_visual_control","jc043/cpl"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/predictable-mdp-abstraction-for-unsupervised","slug":"predictable-mdp-abstraction-for-unsupervised","title":"Predictable MDP Abstraction for Unsupervised Model-Based RL","date":"2023-02-08","arxiv_id":"2302.03921","repositories_listed":2,"syntology":null},{"url":"/paper/the-surprising-effectiveness-of-latent-world","slug":"the-surprising-effectiveness-of-latent-world","title":"The Effectiveness of World Models for Continual Reinforcement Learning","date":"2022-11-29","arxiv_id":"2211.15944","repositories_listed":2,"syntology":null},{"url":"/paper/an-experimental-design-perspective-on-model","slug":"an-experimental-design-perspective-on-model","title":"An Experimental Design Perspective on Model-Based Reinforcement Learning","date":"2021-12-09","arxiv_id":"2112.05244","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":3,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"4 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/an-experimental-design-perspective-on-model#ran","syntology_url":"https://syntology.ai/paper/2112.05244","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.05244"}},"official":null}},{"url":"/paper/gradient-information-matters-in-policy","slug":"gradient-information-matters-in-policy","title":"Gradient Information Matters in Policy Optimization by Back-propagating through Model","date":"2021-09-29","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/planning-in-stochastic-environments-with-a","slug":"planning-in-stochastic-environments-with-a","title":"Planning in Stochastic Environments with a Learned Model","date":"2021-09-29","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/mbrl-lib-a-modular-library-for-model-based","slug":"mbrl-lib-a-modular-library-for-model-based","title":"MBRL-Lib: A Modular Library for Model-based Reinforcement Learning","date":"2021-04-20","arxiv_id":"2104.10159","repositories_listed":2,"syntology":null},{"url":"/paper/online-and-offline-reinforcement-learning-by","slug":"online-and-offline-reinforcement-learning-by","title":"Online and Offline Reinforcement Learning by Planning with a Learned Model","date":"2021-04-13","arxiv_id":"2104.06294","repositories_listed":2,"syntology":null},{"url":"/paper/bellman-a-toolbox-for-model-based","slug":"bellman-a-toolbox-for-model-based","title":"Bellman: A Toolbox for Model-Based Reinforcement Learning in TensorFlow","date":"2021-03-26","arxiv_id":"2103.14407","repositories_listed":2,"syntology":null},{"url":"/paper/improving-model-based-reinforcement-learning","slug":"improving-model-based-reinforcement-learning","title":"Improving Model-Based Reinforcement Learning with Internal State Representations through Self-Supervision","date":"2021-02-10","arxiv_id":"2102.05599","repositories_listed":2,"syntology":null},{"url":"/paper/beyond-prioritized-replay-sampling-states-in","slug":"beyond-prioritized-replay-sampling-states-in","title":"Understanding and Mitigating the Limitations of Prioritized Experience Replay","date":"2020-07-19","arxiv_id":"2007.09569","repositories_listed":2,"syntology":null},{"url":"/paper/the-loca-regret-a-consistent-metric-to","slug":"the-loca-regret-a-consistent-metric-to","title":"The LoCA Regret: A Consistent Metric to Evaluate Model-Based Behavior in Reinforcement Learning","date":"2020-07-07","arxiv_id":"2007.03158","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/the-loca-regret-a-consistent-metric-to#ran","syntology_url":"https://syntology.ai/paper/2007.03158","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.03158"}},"official":{"repos":["chandar-lab/LoCA"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/context-aware-dynamics-model-for","slug":"context-aware-dynamics-model-for","title":"Context-aware Dynamics Model for Generalization in Model-Based Reinforcement Learning","date":"2020-05-14","arxiv_id":"2005.06800","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/context-aware-dynamics-model-for#ran","syntology_url":"https://syntology.ai/paper/2005.06800","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.06800"}},"official":{"repos":["younggyoseo/CaDM"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/objective-mismatch-in-model-based-1","slug":"objective-mismatch-in-model-based-1","title":"Objective Mismatch in Model-based Reinforcement Learning","date":"2020-02-11","arxiv_id":"2002.04523","repositories_listed":2,"syntology":null},{"url":"/paper/learning-to-predict-without-looking-ahead","slug":"learning-to-predict-without-looking-ahead","title":"Learning to Predict Without Looking Ahead: World Models Without Forward Prediction","date":"2019-10-29","arxiv_id":"1910.13038","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/learning-to-predict-without-looking-ahead#ran","syntology_url":"https://syntology.ai/paper/1910.13038","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.13038"}},"official":null}},{"url":"/paper/benchmarking-model-based-reinforcement","slug":"benchmarking-model-based-reinforcement","title":"Benchmarking Model-Based Reinforcement Learning","date":"2019-07-03","arxiv_id":"1907.02057","repositories_listed":2,"syntology":null},{"url":"/paper/baconian-a-unified-opensource-framework-for","slug":"baconian-a-unified-opensource-framework-for","title":"Baconian: A Unified Open-source Framework for Model-Based Reinforcement Learning","date":"2019-04-23","arxiv_id":"1904.10762","repositories_listed":2,"syntology":null},{"url":"/paper/model-based-reinforcement-learning-for-atari","slug":"model-based-reinforcement-learning-for-atari","title":"Model-Based Reinforcement Learning for Atari","date":"2019-03-01","arxiv_id":"1903.00374","repositories_listed":2,"syntology":{"n":21,"n_ran":16,"n_constructed":8,"n_ran_checked":10,"n_instrument":6,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":17,"phrase":"16 ran (of which 8 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/model-based-reinforcement-learning-for-atari#ran","syntology_url":"https://syntology.ai/paper/1903.00374","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.00374"}},"official":{"repos":["tensorflow/tensor2tensor"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/algorithmic-framework-for-model-based-deep","slug":"algorithmic-framework-for-model-based-deep","title":"Algorithmic Framework for Model-based Deep Reinforcement Learning with Theoretical Guarantees","date":"2018-07-10","arxiv_id":"1807.03858","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/algorithmic-framework-for-model-based-deep#ran","syntology_url":"https://syntology.ai/paper/1807.03858","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.03858"}},"official":{"repos":["roosephu/slbo"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-to-adapt-in-dynamic-real-world","slug":"learning-to-adapt-in-dynamic-real-world","title":"Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learning","date":"2018-03-30","arxiv_id":"1803.11347","repositories_listed":2,"syntology":null},{"url":"/paper/model-ensemble-trust-region-policy","slug":"model-ensemble-trust-region-policy","title":"Model-Ensemble Trust-Region Policy Optimization","date":"2018-02-28","arxiv_id":"1802.10592","repositories_listed":2,"syntology":{"n":6,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 6 unverified","sample_list":"/paper/model-ensemble-trust-region-policy#ran","syntology_url":"https://syntology.ai/paper/1802.10592","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.10592"}},"official":{"repos":["thanard/me-trpo"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":6,"ran_from_kinds":[]}}},{"url":"/paper/imagination-augmented-agents-for-deep","slug":"imagination-augmented-agents-for-deep","title":"Imagination-Augmented Agents for Deep Reinforcement Learning","date":"2017-07-19","arxiv_id":"1707.06203","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/imagination-augmented-agents-for-deep#ran","syntology_url":"https://syntology.ai/paper/1707.06203","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1707.06203"}},"official":null}},{"url":"/paper/learning-and-policy-search-in-stochastic","slug":"learning-and-policy-search-in-stochastic","title":"Learning and Policy Search in Stochastic Dynamical Systems with Bayesian Neural Networks","date":"2016-05-23","arxiv_id":"1605.07127","repositories_listed":2,"syntology":null},{"url":"/paper/transdreamerv3-implanting-transformer-in","slug":"transdreamerv3-implanting-transformer-in","title":"TransDreamerV3: Implanting Transformer In DreamerV3","date":"2025-06-20","arxiv_id":"2506.17103","repositories_listed":1,"syntology":null},{"url":"/paper/deep-active-inference-agents-for-delayed-and","slug":"deep-active-inference-agents-for-delayed-and","title":"Deep Active Inference Agents for Delayed and Long-Horizon Environments","date":"2025-05-26","arxiv_id":"2505.19867","repositories_listed":1,"syntology":null},{"url":"/paper/probabilistic-pontryagin-s-maximum-principle","slug":"probabilistic-pontryagin-s-maximum-principle","title":"Probabilistic Pontryagin's Maximum Principle for Continuous-Time Model-Based Reinforcement Learning","date":"2025-04-03","arxiv_id":"2504.02543","repositories_listed":1,"syntology":null},{"url":"/paper/probabilistically-safe-and-efficient-model","slug":"probabilistically-safe-and-efficient-model","title":"Probabilistically safe and efficient model-based Reinforcement Learning","date":"2025-04-01","arxiv_id":"2504.00626","repositories_listed":1,"syntology":null},{"url":"/paper/perspective-shifted-neuro-symbolic-world","slug":"perspective-shifted-neuro-symbolic-world","title":"Perspective-Shifted Neuro-Symbolic World Models: A Framework for Socially-Aware Robot Navigation","date":"2025-03-26","arxiv_id":"2503.20425","repositories_listed":1,"syntology":null},{"url":"/paper/continual-reinforcement-learning-for-hvac","slug":"continual-reinforcement-learning-for-hvac","title":"Continual Reinforcement Learning for HVAC Systems Control: Integrating Hypernetworks and Transfer Learning","date":"2025-03-24","arxiv_id":"2503.19212","repositories_listed":1,"syntology":null},{"url":"/paper/counterfactual-experience-augmented-off","slug":"counterfactual-experience-augmented-off","title":"Counterfactual experience augmented off-policy reinforcement learning","date":"2025-03-18","arxiv_id":"2503.13842","repositories_listed":1,"syntology":null},{"url":"/paper/implementing-spiking-world-model-with-multi","slug":"implementing-spiking-world-model-with-multi","title":"Spiking World Model with Multi-Compartment Neurons for Model-based Reinforcement Learning","date":"2025-03-02","arxiv_id":"2503.00713","repositories_listed":1,"syntology":null},{"url":"/paper/dream-to-drive-with-predictive-individual","slug":"dream-to-drive-with-predictive-individual","title":"Dream to Drive with Predictive Individual World Model","date":"2025-01-28","arxiv_id":"2501.16733","repositories_listed":1,"syntology":null},{"url":"/paper/on-rollouts-in-model-based-reinforcement","slug":"on-rollouts-in-model-based-reinforcement","title":"On Rollouts in Model-Based Reinforcement Learning","date":"2025-01-28","arxiv_id":"2501.16918","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/on-rollouts-in-model-based-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2501.16918","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.16918"}},"official":{"repos":["data-science-in-mechanical-engineering/infoprop"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/diminishing-return-of-value-expansion-methods-1","slug":"diminishing-return-of-value-expansion-methods-1","title":"Diminishing Return of Value Expansion Methods","date":"2024-12-29","arxiv_id":"2412.20537","repositories_listed":1,"syntology":null},{"url":"/paper/simudice-offline-policy-optimization-through","slug":"simudice-offline-policy-optimization-through","title":"SimuDICE: Offline Policy Optimization Through World Model Updates and DICE Estimation","date":"2024-12-09","arxiv_id":"2412.06486","repositories_listed":1,"syntology":null},{"url":"/paper/bayes-adaptive-monte-carlo-tree-search-for","slug":"bayes-adaptive-monte-carlo-tree-search-for","title":"Bayes Adaptive Monte Carlo Tree Search for Offline Model-based Reinforcement Learning","date":"2024-10-15","arxiv_id":"2410.11234","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/bayes-adaptive-monte-carlo-tree-search-for#ran","syntology_url":"https://syntology.ai/paper/2410.11234","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.11234"}},"official":{"repos":["lucascjysdl/offline-rl-kit"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/zero-shot-model-based-reinforcement-learning","slug":"zero-shot-model-based-reinforcement-learning","title":"Zero-shot Model-based Reinforcement Learning using Large Language Models","date":"2024-10-15","arxiv_id":"2410.11711","repositories_listed":1,"syntology":null},{"url":"/paper/drama-mamba-enabled-model-based-reinforcement","slug":"drama-mamba-enabled-model-based-reinforcement","title":"Drama: Mamba-Enabled Model-Based Reinforcement Learning Is Sample and Parameter Efficient","date":"2024-10-11","arxiv_id":"2410.08893","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":2,"n_honours":0,"n_violates":3,"n_no_contract":0,"n_pointer_only":9,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 3 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/drama-mamba-enabled-model-based-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2410.08893","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.08893"}},"official":{"repos":["realwenlongwang/drama"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-to-walk-from-three-minutes-of-real","slug":"learning-to-walk-from-three-minutes-of-real","title":"Learning to Walk from Three Minutes of Real-World Data with Semi-structured Dynamics Models","date":"2024-10-11","arxiv_id":"2410.09163","repositories_listed":1,"syntology":null},{"url":"/paper/bisimulation-metric-for-model-predictive","slug":"bisimulation-metric-for-model-predictive","title":"Bisimulation metric for Model Predictive Control","date":"2024-10-06","arxiv_id":"2410.04553","repositories_listed":1,"syntology":null},{"url":"/paper/learning-discrete-world-models-for-heuristic","slug":"learning-discrete-world-models-for-heuristic","title":"Learning Discrete World Models for Heuristic Search","date":"2024-09-14","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/traffic-expertise-meets-residual-rl-knowledge","slug":"traffic-expertise-meets-residual-rl-knowledge","title":"Traffic expertise meets residual RL: Knowledge-informed model-based residual reinforcement learning for CAV trajectory control","date":"2024-08-30","arxiv_id":"2408.17380","repositories_listed":1,"syntology":null},{"url":"/paper/clue-safe-model-based-rl-hvac-control-using","slug":"clue-safe-model-based-rl-hvac-control-using","title":"A Safe and Data-efficient Model-based Reinforcement Learning System for HVAC Control","date":"2024-07-16","arxiv_id":"2407.12195","repositories_listed":1,"syntology":null},{"url":"/paper/bounding-box-inference-for-error-aware-model","slug":"bounding-box-inference-for-error-aware-model","title":"Bounding-Box Inference for Error-Aware Model-Based Reinforcement Learning","date":"2024-06-23","arxiv_id":"2406.16006","repositories_listed":1,"syntology":null},{"url":"/paper/robust-model-based-reinforcement-learning-1","slug":"robust-model-based-reinforcement-learning-1","title":"Robust Model-Based Reinforcement Learning with an Adversarial Auxiliary Model","date":"2024-06-14","arxiv_id":"2406.09976","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/robust-model-based-reinforcement-learning-1#ran","syntology_url":"https://syntology.ai/paper/2406.09976","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09976"}},"official":{"repos":["rmbpo-eval/rmbpo-eval"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/coprocessor-actor-critic-a-model-based","slug":"coprocessor-actor-critic-a-model-based","title":"Coprocessor Actor Critic: A Model-Based Reinforcement Learning Approach For Adaptive Brain Stimulation","date":"2024-06-10","arxiv_id":"2406.06714","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/coprocessor-actor-critic-a-model-based#ran","syntology_url":"https://syntology.ai/paper/2406.06714","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.06714"}},"official":{"repos":["michelllepan/neural-coprocessors"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/trust-the-model-where-it-trusts-itself-model","slug":"trust-the-model-where-it-trusts-itself-model","title":"Trust the Model Where It Trusts Itself -- Model-Based Actor-Critic with Uncertainty-Aware Rollout Adaption","date":"2024-05-29","arxiv_id":"2405.19014","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/trust-the-model-where-it-trusts-itself-model#ran","syntology_url":"https://syntology.ai/paper/2405.19014","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.19014"}},"official":{"repos":["Data-Science-in-Mechanical-Engineering/macura"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/safe-deep-model-based-reinforcement-learning","slug":"safe-deep-model-based-reinforcement-learning","title":"Safe Deep Model-Based Reinforcement Learning with Lyapunov Functions","date":"2024-05-25","arxiv_id":"2405.16184","repositories_listed":1,"syntology":null},{"url":"/paper/generating-code-world-models-with-large","slug":"generating-code-world-models-with-large","title":"Generating Code World Models with Large Language Models Guided by Monte Carlo Tree Search","date":"2024-05-24","arxiv_id":"2405.15383","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/generating-code-world-models-with-large#ran","syntology_url":"https://syntology.ai/paper/2405.15383","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.15383"}},"official":{"repos":["nicoladainese96/code-world-models"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/ivideogpt-interactive-videogpts-are-scalable","slug":"ivideogpt-interactive-videogpts-are-scalable","title":"iVideoGPT: Interactive VideoGPTs are Scalable World Models","date":"2024-05-24","arxiv_id":"2405.15223","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/ivideogpt-interactive-videogpts-are-scalable#ran","syntology_url":"https://syntology.ai/paper/2405.15223","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.15223"}},"official":{"repos":["thuml/iVideoGPT"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/neuromorphic-dreaming-a-pathway-to-efficient","slug":"neuromorphic-dreaming-a-pathway-to-efficient","title":"Neuromorphic dreaming: A pathway to efficient learning in artificial agents","date":"2024-05-24","arxiv_id":"2405.15616","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-multi-agent-reinforcement-learning","slug":"efficient-multi-agent-reinforcement-learning","title":"Efficient Multi-agent Reinforcement Learning by Planning","date":"2024-05-20","arxiv_id":"2405.11778","repositories_listed":1,"syntology":null},{"url":"/paper/learning-latent-dynamic-robust","slug":"learning-latent-dynamic-robust","title":"Learning Latent Dynamic Robust Representations for World Models","date":"2024-05-10","arxiv_id":"2405.06263","repositories_listed":1,"syntology":null},{"url":"/paper/supercompiler-code-optimization-with-zero","slug":"supercompiler-code-optimization-with-zero","title":"CompilerDream: Learning a Compiler World Model for General Code Optimization","date":"2024-04-24","arxiv_id":"2404.16077","repositories_listed":1,"syntology":null},{"url":"/paper/exploiting-symmetry-in-dynamics-for-model","slug":"exploiting-symmetry-in-dynamics-for-model","title":"Exploiting Symmetry in Dynamics for Model-Based Reinforcement Learning with Asymmetric Rewards","date":"2024-03-27","arxiv_id":"2403.19024","repositories_listed":1,"syntology":null},{"url":"/paper/deep-gaussian-covariance-network-with","slug":"deep-gaussian-covariance-network-with","title":"Deep Gaussian Covariance Network with Trajectory Sampling for Data-Efficient Policy Search","date":"2024-03-23","arxiv_id":"2403.15908","repositories_listed":1,"syntology":null},{"url":"/paper/sindy-rl-interpretable-and-efficient-model","slug":"sindy-rl-interpretable-and-efficient-model","title":"SINDy-RL: Interpretable and Efficient Model-Based Reinforcement Learning","date":"2024-03-14","arxiv_id":"2403.09110","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/sindy-rl-interpretable-and-efficient-model#ran","syntology_url":"https://syntology.ai/paper/2403.09110","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.09110"}},"official":{"repos":["nzolman/sindy-rl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mastering-memory-tasks-with-world-models","slug":"mastering-memory-tasks-with-world-models","title":"Mastering Memory Tasks with World Models","date":"2024-03-07","arxiv_id":"2403.04253","repositories_listed":1,"syntology":{"n":12,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":6,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":3,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/mastering-memory-tasks-with-world-models#ran","syntology_url":"https://syntology.ai/paper/2403.04253","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.04253"}},"official":{"repos":["chandar-lab/Recall2Imagine"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/go-beyond-black-box-policies-rethinking-the","slug":"go-beyond-black-box-policies-rethinking-the","title":"Go Beyond Black-box Policies: Rethinking the Design of Learning Agent for Interpretable and Verifiable HVAC Control","date":"2024-02-29","arxiv_id":"2403.00172","repositories_listed":1,"syntology":null},{"url":"/paper/model-based-deep-reinforcement-learning-for-2","slug":"model-based-deep-reinforcement-learning-for-2","title":"Model-based deep reinforcement learning for accelerated learning from flow simulations","date":"2024-02-26","arxiv_id":"2402.16543","repositories_listed":1,"syntology":null},{"url":"/paper/a-distributional-analogue-to-the-successor","slug":"a-distributional-analogue-to-the-successor","title":"A Distributional Analogue to the Successor Representation","date":"2024-02-13","arxiv_id":"2402.08530","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/a-distributional-analogue-to-the-successor#ran","syntology_url":"https://syntology.ai/paper/2402.08530","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.08530"}},"official":{"repos":["jessefarebro/distributional-sr"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/smx-sequential-monte-carlo-planning-for","slug":"smx-sequential-monte-carlo-planning-for","title":"SPO: Sequential Monte Carlo Policy Optimisation","date":"2024-02-12","arxiv_id":"2402.07963","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/smx-sequential-monte-carlo-planning-for#ran","syntology_url":"https://syntology.ai/paper/2402.07963","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.07963"}},"official":null}},{"url":"/paper/augmenting-replay-in-world-models-for","slug":"augmenting-replay-in-world-models-for","title":"Augmenting Replay in World Models for Continual Reinforcement Learning","date":"2024-01-30","arxiv_id":"2401.16650","repositories_listed":1,"syntology":null},{"url":"/paper/covo-mpc-theoretical-analysis-of-sampling","slug":"covo-mpc-theoretical-analysis-of-sampling","title":"CoVO-MPC: Theoretical Analysis of Sampling-based MPC and Optimal Covariance Design","date":"2024-01-14","arxiv_id":"2401.07369","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":0,"n_honours":2,"n_violates":1,"n_no_contract":1,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 1 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/covo-mpc-theoretical-analysis-of-sampling#ran","syntology_url":"https://syntology.ai/paper/2401.07369","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.07369"}},"official":{"repos":["LeCAR-Lab/CoVO-MPC"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/laboratory-experiments-of-model-based","slug":"laboratory-experiments-of-model-based","title":"Laboratory Experiments of Model-based Reinforcement Learning for Adaptive Optics Control","date":"2023-12-30","arxiv_id":"2401.00242","repositories_listed":1,"syntology":null},{"url":"/paper/sample-efficient-learning-to-solve-a-real","slug":"sample-efficient-learning-to-solve-a-real","title":"Sample-Efficient Learning to Solve a Real-World Labyrinth Game Using Data-Augmented Model-Based Reinforcement Learning","date":"2023-12-15","arxiv_id":"2312.09906","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-learning-with-model-predictive","slug":"reinforcement-learning-with-model-predictive","title":"Reinforcement Learning with Model Predictive Control for Highway Ramp Metering","date":"2023-11-15","arxiv_id":"2311.08820","repositories_listed":1,"syntology":null},{"url":"/paper/benchmark-generation-framework-with","slug":"benchmark-generation-framework-with","title":"Benchmark Generation Framework with Customizable Distortions for Image Classifier Robustness","date":"2023-10-28","arxiv_id":"2310.18626","repositories_listed":1,"syntology":null},{"url":"/paper/storm-efficient-stochastic-transformer-based-1","slug":"storm-efficient-stochastic-transformer-based-1","title":"STORM: Efficient Stochastic Transformer based World Models for Reinforcement Learning","date":"2023-10-14","arxiv_id":"2310.09615","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":3,"n_no_contract":2,"n_pointer_only":10,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 3 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/storm-efficient-stochastic-transformer-based-1#ran","syntology_url":"https://syntology.ai/paper/2310.09615","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.09615"}},"official":{"repos":["weipu-zhang/storm"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/a-unified-view-on-solving-objective-mismatch","slug":"a-unified-view-on-solving-objective-mismatch","title":"A Unified View on Solving Objective Mismatch in Model-Based Reinforcement Learning","date":"2023-10-10","arxiv_id":"2310.06253","repositories_listed":1,"syntology":null},{"url":"/paper/probabilistic-reach-avoid-for-bayesian-neural","slug":"probabilistic-reach-avoid-for-bayesian-neural","title":"Probabilistic Reach-Avoid for Bayesian Neural Networks","date":"2023-10-03","arxiv_id":"2310.01951","repositories_listed":1,"syntology":null},{"url":"/paper/combining-spatial-and-temporal-abstraction-in","slug":"combining-spatial-and-temporal-abstraction-in","title":"Consciousness-Inspired Spatio-Temporal Abstractions for Better Generalization in Reinforcement Learning","date":"2023-09-30","arxiv_id":"2310.00229","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/combining-spatial-and-temporal-abstraction-in#ran","syntology_url":"https://syntology.ai/paper/2310.00229","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.00229"}},"official":{"repos":["mila-iqia/skipper"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/harmony-world-models-boosting-sample","slug":"harmony-world-models-boosting-sample","title":"HarmonyDream: Task Harmonization Inside World Models","date":"2023-09-30","arxiv_id":"2310.00344","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/harmony-world-models-boosting-sample#ran","syntology_url":"https://syntology.ai/paper/2310.00344","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.00344"}},"official":{"repos":["thuml/harmonydream"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/practical-probabilistic-model-based-deep","slug":"practical-probabilistic-model-based-deep","title":"Practical Probabilistic Model-based Deep Reinforcement Learning by Integrating Dropout Uncertainty and Trajectory Sampling","date":"2023-09-20","arxiv_id":"2309.11089","repositories_listed":1,"syntology":null},{"url":"/paper/repo-resilient-model-based-reinforcement","slug":"repo-resilient-model-based-reinforcement","title":"RePo: Resilient Model-Based Reinforcement Learning by Regularizing Posterior Predictability","date":"2023-08-31","arxiv_id":"2309.00082","repositories_listed":1,"syntology":null},{"url":"/paper/the-power-of-meme-adversarial-malware","slug":"the-power-of-meme-adversarial-malware","title":"The Power of MEME: Adversarial Malware Creation with Model-Based Reinforcement Learning","date":"2023-08-31","arxiv_id":"2308.16562","repositories_listed":1,"syntology":null},{"url":"/paper/value-distributional-model-based","slug":"value-distributional-model-based","title":"Value-Distributional Model-Based Reinforcement Learning","date":"2023-08-12","arxiv_id":"2308.06590","repositories_listed":1,"syntology":null},{"url":"/paper/learning-disentangled-discrete","slug":"learning-disentangled-discrete","title":"Learning Disentangled Discrete Representations","date":"2023-07-26","arxiv_id":"2307.14151","repositories_listed":1,"syntology":null},{"url":"/paper/mode-constrained-model-based-reinforcement","slug":"mode-constrained-model-based-reinforcement","title":"Mode-constrained Model-based Reinforcement Learning via Gaussian Processes","date":"2023-07-25","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/curious-replay-for-model-based-adaptation","slug":"curious-replay-for-model-based-adaptation","title":"Curious Replay for Model-based Adaptation","date":"2023-06-28","arxiv_id":"2306.15934","repositories_listed":1,"syntology":null},{"url":"/paper/vid2act-activate-offline-videos-for-visual-rl","slug":"vid2act-activate-offline-videos-for-visual-rl","title":"Model-Based Reinforcement Learning with Multi-Task Offline Pretraining","date":"2023-06-06","arxiv_id":"2306.03360","repositories_listed":1,"syntology":null},{"url":"/paper/pre-training-contextualized-world-models-with-1","slug":"pre-training-contextualized-world-models-with-1","title":"Pre-training Contextualized World Models with In-the-wild Videos for Reinforcement Learning","date":"2023-05-29","arxiv_id":"2305.18499","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/pre-training-contextualized-world-models-with-1#ran","syntology_url":"https://syntology.ai/paper/2305.18499","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18499"}},"official":{"repos":["thuml/ContextWM"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/adaptive-pd-control-using-deep-reinforcement","slug":"adaptive-pd-control-using-deep-reinforcement","title":"Adaptive PD Control using Deep Reinforcement Learning for Local-Remote Teleoperation with Stochastic Time Delays","date":"2023-05-26","arxiv_id":"2305.16979","repositories_listed":1,"syntology":null},{"url":"/paper/posterior-sampling-for-deep-reinforcement","slug":"posterior-sampling-for-deep-reinforcement","title":"Posterior Sampling for Deep Reinforcement Learning","date":"2023-04-30","arxiv_id":"2305.00477","repositories_listed":1,"syntology":null}],"syntology_records":35,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":72,"papers_where_code_ran_first_page":"/task/model-based-reinforcement-learning/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":8,"url":"/task/model-based-reinforcement-learning/papers/2","json":"/task/model-based-reinforcement-learning/papers/2.json","rows":100},{"order":"archive","page":3,"of":8,"url":"/task/model-based-reinforcement-learning/papers/3","json":"/task/model-based-reinforcement-learning/papers/3.json","rows":100},{"order":"archive","page":4,"of":8,"url":"/task/model-based-reinforcement-learning/papers/4","json":"/task/model-based-reinforcement-learning/papers/4.json","rows":100},{"order":"archive","page":5,"of":8,"url":"/task/model-based-reinforcement-learning/papers/5","json":"/task/model-based-reinforcement-learning/papers/5.json","rows":100},{"order":"archive","page":6,"of":8,"url":"/task/model-based-reinforcement-learning/papers/6","json":"/task/model-based-reinforcement-learning/papers/6.json","rows":100},{"order":"archive","page":7,"of":8,"url":"/task/model-based-reinforcement-learning/papers/7","json":"/task/model-based-reinforcement-learning/papers/7.json","rows":100},{"order":"archive","page":8,"of":8,"url":"/task/model-based-reinforcement-learning/papers/8","json":"/task/model-based-reinforcement-learning/papers/8.json","rows":8},{"order":"ran","page":1,"of":1,"url":"/task/model-based-reinforcement-learning/papers/ran/1","json":"/task/model-based-reinforcement-learning/papers/ran/1.json","rows":72}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"dc6ab9b6c29e907cb3c53983fbb01a9b97118f1f54402992dda0f6374760e7c2","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}